The Security Evaluation of ATM Information System Based on Bayesian Regularization

Air Traffic Management (ATM)system is enticing targets of cyber-attacks since 9.11 event, and the securitysituation of ATM information system is closely related to the safety flight ofair transportation. In this paper, an approach of security evaluation for ATMsystem is proposed based on artificial neural network (ANN). The proposed approachcombines neural networks with Bayesian regularization to simulate ATM system inANN. An indicator system of security situation for ATM system is established asthe input of ANN, and the output is system security level, which is obtained bytraining the ANN with the daily recoded data of ATM system. Experimentalresults show that the proposed method has a certain precision and practicality.

[1]  Fu Yu.  Application of Bayesian network inference in security risk assessment of information systems , 2007 .

[2]  Yuansheng Huang,et al.  Fuzzy Comprehensive Evaluation Mode on the Investment Risk of Real Estate Based on BP Neural Network and Expert System , 2009, 2009 International Conference on E-Business and Information System Security.

[3]  Dong Dou-dou.  Probabilistic safety assessment research based on Bayesian networks , 2006 .

[4]  Yi Jiang,et al.  Optimizing for Large Time Delay Systems by BP Neural Network and Evolutionary Algorithm Improving , 2011, J. Softw..

[5]  P. Lisboa,et al.  External Validation of a Bayesian Neural Network Model in Survival Analysis , 2008, 2008 Seventh International Conference on Machine Learning and Applications.

[6]  Robert Hoffman,et al.  Air Traffic Management , 2011 .

[7]  Gustavo Ramos,et al.  Análisis de Confiabilidad de Sistemas Industriales Aplicando Redes Bayesianas Considerando Aspectos de PQ y Seguridad - Caso de Estudio Sistema IEEE 493 , 2007 .

[8]  Eric Filiol,et al.  New Trends in Security Evaluation of Bayesian Network-Based Malware Detection Models , 2012, 2012 45th Hawaii International Conference on System Sciences.

[9]  Dong-Mei Zhao,et al.  Method of risk evaluation of information security based on neural networks , 2009, 2009 International Conference on Machine Learning and Cybernetics.

[10]  She Yu-mei.  Approach to Information Systems Security Risk Assessment Based on Fuzzy-BP Neural Network , 2011 .

[11]  T. McParland,et al.  Securing air-ground communications , 2001, 20th DASC. 20th Digital Avionics Systems Conference (Cat. No.01CH37219).

[12]  Qiongxin Liu,et al.  A BP Neural Network Model Based on Genetic Algorithm for Comprehensive Evaluation , 2011, 2011 Third Pacific-Asia Conference on Circuits, Communications and System (PACCS).

[13]  K. S. Swarup,et al.  ANN approach assesses system security , 2002 .

[14]  Mingsheng Liu,et al.  Research on Applying the Theory of Wavelet Neural Network and Entropy-Grey Association to the Security Risk Assessment for E-Government Information System , 2011, J. Comput..

[15]  Gustavo Andres Ramos L.,et al.  Reliability Analysis of Industrial Electrical Systems Using Bayesian Networks Considering Power Quality and Security Characteristics Applied to the IEEE 493 Standard Network , 2007, IEEE Latin America Transactions.

[16]  Wenxian Xiao,et al.  Information Security Risk Assessment Based on Information Measure and Fuzzy Clustering , 2011, J. Softw..

[17]  Cai Hong-liu.  A Comprehensive Security Evaluation Model of Information Systems Based on Artificial Neural Networks , 2008 .

[18]  Yan Cheng-hua.  The Method of Information Security Risk Assessment Using Bayesian Networks , 2006 .

[19]  Sandip C. Patel,et al.  A Risk-Assessment Model for Cyber Attacks on Information Systems , 2010, J. Comput..

[20]  A. Bell.  Radio: The Style of News Language , 1982 .

[21]  Xie Xiaohui,et al.  A Robust Fingerprint Minutiae Matching Method , 2005 .